AI Agent Skill Repository

AI Agent Skills Directory

Browse reusable skills for Codex, Claude Code, Cursor, finance, research, web scraping, PPT, football analytics, data, marketing, design, and more.

Browse by scenario

Real skills, grouped by the work your agent needs to finish.

Each directory entry links to real skill pages with GitHub adoption, trust score, install handoff, risk notes, and agent-readable metadata. Use these as starting points when you want a shortlist before asking an agent to install anything.

Design to deployment

Frontend and UI skills

Design direction, Figma implementation, UI review, React performance, browser QA, and safe preview deployments.

  • Frontend Design167K stars

    Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product…

    Trust 88Quality 100design-creative
  • Apple Design18K stars

    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or…

    Trust 91Quality 100design-creative
  • Cli16K stars

    The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers…

    Trust 88Quality 100productivity

Codex, Claude Code, Cursor

Coding agent skills

Code review, repo inspection, testing, planning, shipping, and engineering workflows for coding agents.

  • Open Design85K stars

    🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design…

    Trust 91Quality 100agent-skills
  • Agent Skills86K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills
  • Implement176K stars

    Execute an approved engineering ticket with tests, review, and a branch commit.

    Trust 88Quality 100coding-agents

Documents and knowledge

Research and RAG skills

Research, recent-events briefings, PDF parsing, markdown conversion, RAG ingestion, and knowledge workflows.

  • Quarkdown16K stars

    🪐 Markdown with superpowers: from ideas to papers, presentations, websites, books, and knowledge bases.

    Trust 89Quality 100document-processing
  • Organize ideas and collaborate using Markdown, a lightweight language for text formatting.

    Trust 88Quality 94document-processing
  • Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations ou…

    Trust 88Quality 97rag-knowledge

Markets and quant

Finance and trading skills

Stock analysis, market research, quant backtesting, financial data, and investment research skills.

  • Qlib44K stars

    Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exp…

    Trust 89Quality 100finance
  • Vectorbt7.9K stars

    The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finis…

    Trust 86Quality 96finance

Crawlers and extraction

Web scraping skills

Crawling, scraping, extraction, browser automation, structured data capture, and website-to-markdown workflows.

  • Pandora Box1.2K stars

    A Simple Mihomo GUI. 一个简易的 Mihomo 桌面客户端

    Trust 85Quality 93web-automation
  • ImageToolbox13K stars

    🖼️ Image Toolbox is a powerful app for advanced image manipulation. It offers dozens of features, from basic…

    Trust 89Quality 100document-processing
  • PdfPig2.5K stars

    Read and extract text and other content from PDFs in C# (port of PDFBox)

    Trust 85Quality 96document-processing

Slides and decks

PPT and presentation skills

Presentation generation, editable PPTX, slide decks, speaker notes, and visual storytelling workflows.

  • Html Anything6.7K stars

    ✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (maga…

    Trust 84Quality 100agent-skills

Prompts, B-roll, explainers

Video creation skills

Video-generation prompts, B-roll, Vox-style explainers, camera direction, captions, and creative-production workflows.

  • Seedance 2.0 prompt skill,使用该Skill生成Seedance 2.0 视频提示词

    Trust 82Quality 85media
  • VideoClaw1.4K stars

    🚀 AI 全自动化视频生成员工 | Your First AIGC Coworker. Chat an Idea. Get a Film. 🦞

    Trust 85Quality 94media-automation

Images, video, UI

Design and creative skills

Image, video, creative production, UI design, multimodal generation, and visual workflow skills.

  • Robosat2.1K stars

    Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, ro…

    Trust 88Quality 95ml-automation
  • Meshroom13K stars

    Node-based Visual Programming Toolbox

    Trust 85Quality 100automation
  • ODS3.3K stars

    Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and…

    Trust 85Quality 100agent-frameworks

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

221

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

221 quality220 maintained

Research

Research and knowledge work

87

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

87 quality87 maintained

Presentation

Presentation and deck workflows

1

PPTX generation, HTML slides, pitch decks, speaker notes, and presentation workflow skills.

1 quality1 maintained

Finance

Finance and quant workflows

34

Market data, SEC filings, portfolio analysis, quant research, backtesting, and risk workflows.

34 quality34 maintained

Marketing

Marketing and growth automation

14

SEO, content operations, lead generation, CRM, email automation, analytics, and growth workflows.

14 quality14 maintained

Design

Design and creative production

61

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

61 quality61 maintained

Data

Data, BI, and analytics

38

CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis.

38 quality38 maintained

Legal

Legal, policy, and compliance

18

Contract analysis, privacy, policy review, compliance checks, governance, and document risk review.

18 quality18 maintained

Education

Education and tutoring

5

Tutoring, course generation, quizzes, learning analytics, classrooms, and teaching workflows.

5 quality5 maintained

World Cup

Football and World Cup analytics

2

Football data, World Cup dashboards, xG, match prediction, scouting, and sports analytics.

2 quality2 maintained

High-intent entry points

Start from the task, not a keyword list.

These shortcuts use the same trust, supply, and relevance signals as the registry API, so humans and agents land on a useful shortlist faster.

Agent-readable index

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 468 ranked candidates matching "idea-box"

Best blend of quality, stars, freshness, and agent usage

1

OpenSandbox

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Secure, Fast, and Extensible Sandbox runtime for AI agents.

$ npx skills add alibaba/OpenSandbox
11.6K stars72 quality88 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation

CLI + Codex · 4 targets

pythonai-agents
by alibabaDetailsQuick view
2

Boxlite

VERIFIEDEXCELLENT · 96TRUST · 87SAFE · REVIEWEDCODING

Compute substrate for AI agents: lightweight enough to live on your laptop, elastic enough to scale into the cloud and unleash unlimited resources.

$ npx skills add boxlite-ai/boxlite
2.1K stars65 quality87 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

CLI + Codex · 4 targets

typescriptai-agents
by boxlite-aiDetailsQuick view
3

Chatterbox TTS Server

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDDESIGN

Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice clonin…

$ npx skills add devnen/Chatterbox-TTS-Server
1.3K stars64 quality86 trustReviewedOpenAI Agents3mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

OpenAI Agents + CLI · 4 targets

pythonvoice
by devnenDetailsQuick view
4

Chatbox

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Powerful AI Client

$ npx skills add chatboxai/chatbox
40.5K stars75 quality88 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

typescriptchatbot
by chatboxaiDetailsQuick view
5

Mailinabox

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

Mail-in-a-Box helps individuals take back control of their email by defining a one-click, easy-to-deploy SMTP+everything else server: a mail server in a box.

$ npx skills add mail-in-a-box/mailinabox
15.3K stars73 quality90 trustReviewed3mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation

CLI + Codex · 4 targets

pythonemail
by mail-in-a-boxDetailsQuick view
6

ImageToolbox

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDRESEARCH

🖼️ Image Toolbox is a powerful app for advanced image manipulation. It offers dozens of features, from basic tools like crop and draw to filters, OCR, and a wide range…

$ npx skills add T8RIN/ImageToolbox
13.2K stars72 quality89 trustReviewed with permission notes2mo since pushNeeds review
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Financial research output is not financial advice; require human review before…
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Document processing

CLI + Codex · 4 targets

kotlinpdf
by T8RINDetailsQuick view
7

Inbox Zero

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDRESEARCH

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

$ npx skills add elie222/inbox-zero
11.3K stars72 quality87 trustReviewedOpenAI Agents2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

OpenAI Agents + CLI · 4 targets

typescriptproductivity
by elie222DetailsQuick view
8

Scanners Box

VERIFIEDEXCELLENT · 97TRUST · 86SAFE · REVIEWEDCODING

A powerful and open-source toolkit for hackers and security automation - 安全行业从业者自研开源扫描器合辑

$ npx skills add We5ter/Scanners-Box
9.0K stars69 quality86 trustReviewed1mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

CLI + Codex · 4 targets

static-analysis
by We5terDetailsQuick view
9

Boxmot

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDDESIGN

BoxMOT: Pluggable python and c++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

$ npx skills add mikel-brostrom/boxmot
8.2K stars69 quality89 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by mikel-brostromDetailsQuick view
10

Aidea

VERIFIEDEXCELLENT · 94TRUST · 88SAFE · REVIEWEDCODING

An APP that integrates mainstream large language models and image generation models, built with Flutter, with fully open-source code.

$ npx skills add mylxsw/aidea
6.9K stars62 quality88 trustReviewedOpenAI Agents5mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

OpenAI Agents + CLI · 4 targets

dartchatbot
by mylxswDetailsQuick view
11

Sysbox

VERIFIEDEXCELLENT · 98TRUST · 83SAFE · REVIEWEDCODING

An open-source, next-generation "runc" that empowers rootless containers to run workloads such as Systemd, Docker, Kubernetes, just like VMs.

$ npx skills add nestybox/sysbox
3.7K stars67 quality83 trustReviewed with permission notes3mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

shelldevops
by nestyboxDetailsQuick view
12

VCPToolBox

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDCODING

VCP 部署在 AI 模型 API 与前端应用之间,是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架,将原本“无状态、无记忆、无工具调用能力”的大语言模型,彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

$ npx skills add lioensky/VCPToolBox
2.2K stars65 quality84 trustReviewed28d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

CLI + Codex · 4 targets

javascriptai-agents
by lioenskyDetailsQuick view
13

Omnibox

VERIFIEDEXCELLENT · 94TRUST · 85SAFE · REVIEWEDRESEARCH

Collect, organize, use, and share, all in OmniBox.

$ npx skills add import-ai/omnibox
1.4K stars64 quality85 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

CLI + Codex · 4 targets

pythonrag
by import-aiDetailsQuick view
14

Sandbox Agent

VERIFIEDEXCELLENT · 94TRUST · 85SAFE · REVIEWEDCODING

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

$ npx skills add rivet-dev/sandbox-agent
1.4K stars64 quality85 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

typescriptcoding-agent
by rivet-devDetailsQuick view
15

Waveboxapp

VERIFIEDEXCELLENT · 98TRUST · 84SAFE · REVIEWEDMARKETING

Wavebox, the revolutionary and feature-rich Chromium browser that's built for productive working across Google Workspaces, Microsoft Teams, ClickUp, Monday, Atlassian, A…

$ npx skills add wavebox/waveboxapp
1.4K stars64 quality84 trustReviewedBrowser agents24d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Email and calendar

Browser agents + CLI · 4 targets

javascriptemail
by waveboxDetailsQuick view
16

Responsible AI Toolbox

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · VERIFIEDDATA

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI sys…

$ npx skills add microsoft/responsible-ai-toolbox
1.8K stars61 quality86 trustVerified3mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Data analysis

CLI + Codex · 4 targets

typescriptdata-analysis
by microsoftDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API